{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OXPQH6VYMVCEDLOSIPEFZZNHEU","short_pith_number":"pith:OXPQH6VY","canonical_record":{"source":{"id":"2409.08039","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-12T13:42:04Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"7fba3fe654e3a5b6fb28b7c08839007ce45a08a1521a135e9d9460da440fe703","abstract_canon_sha256":"14dd1082d5bed400a25a871e13940105d65ef81c5b17b8f9c714d483aeded671"},"schema_version":"1.0"},"canonical_sha256":"75df03fab8654441add243c85ce5a725031e910fd98a0d7f898f3bc9930f7015","source":{"kind":"arxiv","id":"2409.08039","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08039","created_at":"2026-07-05T09:20:02Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08039v2","created_at":"2026-07-05T09:20:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08039","created_at":"2026-07-05T09:20:02Z"},{"alias_kind":"pith_short_12","alias_value":"OXPQH6VYMVCE","created_at":"2026-07-05T09:20:02Z"},{"alias_kind":"pith_short_16","alias_value":"OXPQH6VYMVCEDLOS","created_at":"2026-07-05T09:20:02Z"},{"alias_kind":"pith_short_8","alias_value":"OXPQH6VY","created_at":"2026-07-05T09:20:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OXPQH6VYMVCEDLOSIPEFZZNHEU","target":"record","payload":{"canonical_record":{"source":{"id":"2409.08039","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-12T13:42:04Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"7fba3fe654e3a5b6fb28b7c08839007ce45a08a1521a135e9d9460da440fe703","abstract_canon_sha256":"14dd1082d5bed400a25a871e13940105d65ef81c5b17b8f9c714d483aeded671"},"schema_version":"1.0"},"canonical_sha256":"75df03fab8654441add243c85ce5a725031e910fd98a0d7f898f3bc9930f7015","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:02.610737Z","signature_b64":"xReml/vZNo2DKk1Io5OqCnN3ZStA5pJBdgbFMsJbfTA00ehjhegTwcMbL+Ck9IvHxWns3w8ZIA/GlcRkl6bRDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75df03fab8654441add243c85ce5a725031e910fd98a0d7f898f3bc9930f7015","last_reissued_at":"2026-07-05T09:20:02.610278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:02.610278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.08039","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:20:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d/J1+AdSrJxzp8biQoj7tuwpGcjWFD8A9T8MnL0+5ARpBgqcxi94M2fkYxK9o3vtNkUGwTEBMQjwUpfBDg+4Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:00:08.058746Z"},"content_sha256":"6d80059245c7dc47271ef54690fd5f444f6795dd5a678a7f9c7b5c3bea69faad","schema_version":"1.0","event_id":"sha256:6d80059245c7dc47271ef54690fd5f444f6795dd5a678a7f9c7b5c3bea69faad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OXPQH6VYMVCEDLOSIPEFZZNHEU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zero-Shot Sing Voice Conversion: built upon clustering-based phoneme representations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Fengrun Zhang, Tatsuya Kawahara, Wangjin Zhou, Wenhao Guan, Yiming Liu, Yi Zhao","submitted_at":"2024-09-12T13:42:04Z","abstract_excerpt":"This study presents an innovative Zero-Shot any-to-any Singing Voice Conversion (SVC) method, leveraging a novel clustering-based phoneme representation to effectively separate content, timbre, and singing style. This approach enables precise voice characteristic manipulation. We discovered that datasets with fewer recordings per artist are more susceptible to timbre leakage. Extensive testing on over 10,000 hours of singing and user feedback revealed our model significantly improves sound quality and timbre accuracy, aligning with our objectives and advancing voice conversion technology. Furt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08039","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.08039/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:20:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AlWX8BUebwzjMitcFI0bRzpsvysinGDQzMNaW/GupttrN2oretUUqQ1KAV1EMo6gp8LCdLLi1tLe3j6++LBGDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:00:08.059257Z"},"content_sha256":"e55ff82a4791e73ce4ad4c4a469ad72ae432131c93e3283f6534f050f67b8618","schema_version":"1.0","event_id":"sha256:e55ff82a4791e73ce4ad4c4a469ad72ae432131c93e3283f6534f050f67b8618"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OXPQH6VYMVCEDLOSIPEFZZNHEU/bundle.json","state_url":"https://pith.science/pith/OXPQH6VYMVCEDLOSIPEFZZNHEU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OXPQH6VYMVCEDLOSIPEFZZNHEU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T18:00:08Z","links":{"resolver":"https://pith.science/pith/OXPQH6VYMVCEDLOSIPEFZZNHEU","bundle":"https://pith.science/pith/OXPQH6VYMVCEDLOSIPEFZZNHEU/bundle.json","state":"https://pith.science/pith/OXPQH6VYMVCEDLOSIPEFZZNHEU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OXPQH6VYMVCEDLOSIPEFZZNHEU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OXPQH6VYMVCEDLOSIPEFZZNHEU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"14dd1082d5bed400a25a871e13940105d65ef81c5b17b8f9c714d483aeded671","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-12T13:42:04Z","title_canon_sha256":"7fba3fe654e3a5b6fb28b7c08839007ce45a08a1521a135e9d9460da440fe703"},"schema_version":"1.0","source":{"id":"2409.08039","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08039","created_at":"2026-07-05T09:20:02Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08039v2","created_at":"2026-07-05T09:20:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08039","created_at":"2026-07-05T09:20:02Z"},{"alias_kind":"pith_short_12","alias_value":"OXPQH6VYMVCE","created_at":"2026-07-05T09:20:02Z"},{"alias_kind":"pith_short_16","alias_value":"OXPQH6VYMVCEDLOS","created_at":"2026-07-05T09:20:02Z"},{"alias_kind":"pith_short_8","alias_value":"OXPQH6VY","created_at":"2026-07-05T09:20:02Z"}],"graph_snapshots":[{"event_id":"sha256:e55ff82a4791e73ce4ad4c4a469ad72ae432131c93e3283f6534f050f67b8618","target":"graph","created_at":"2026-07-05T09:20:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.08039/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study presents an innovative Zero-Shot any-to-any Singing Voice Conversion (SVC) method, leveraging a novel clustering-based phoneme representation to effectively separate content, timbre, and singing style. This approach enables precise voice characteristic manipulation. We discovered that datasets with fewer recordings per artist are more susceptible to timbre leakage. Extensive testing on over 10,000 hours of singing and user feedback revealed our model significantly improves sound quality and timbre accuracy, aligning with our objectives and advancing voice conversion technology. Furt","authors_text":"Fengrun Zhang, Tatsuya Kawahara, Wangjin Zhou, Wenhao Guan, Yiming Liu, Yi Zhao","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-12T13:42:04Z","title":"Zero-Shot Sing Voice Conversion: built upon clustering-based phoneme representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08039","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6d80059245c7dc47271ef54690fd5f444f6795dd5a678a7f9c7b5c3bea69faad","target":"record","created_at":"2026-07-05T09:20:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"14dd1082d5bed400a25a871e13940105d65ef81c5b17b8f9c714d483aeded671","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-12T13:42:04Z","title_canon_sha256":"7fba3fe654e3a5b6fb28b7c08839007ce45a08a1521a135e9d9460da440fe703"},"schema_version":"1.0","source":{"id":"2409.08039","kind":"arxiv","version":2}},"canonical_sha256":"75df03fab8654441add243c85ce5a725031e910fd98a0d7f898f3bc9930f7015","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75df03fab8654441add243c85ce5a725031e910fd98a0d7f898f3bc9930f7015","first_computed_at":"2026-07-05T09:20:02.610278Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:02.610278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xReml/vZNo2DKk1Io5OqCnN3ZStA5pJBdgbFMsJbfTA00ehjhegTwcMbL+Ck9IvHxWns3w8ZIA/GlcRkl6bRDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:02.610737Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.08039","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d80059245c7dc47271ef54690fd5f444f6795dd5a678a7f9c7b5c3bea69faad","sha256:e55ff82a4791e73ce4ad4c4a469ad72ae432131c93e3283f6534f050f67b8618"],"state_sha256":"12dfa2c412e14e1dfc001f1f01956702562a04abdb32c825245d598fa0338a39"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HqW54HkCCjqT/s7JT3LSHTSvze51A92dF4esYLAM2lJpgrjqSJlsZFi7KREKUBC3OZbRm5CAWdFeMpxwZg53Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:00:08.063377Z","bundle_sha256":"38326cbe124989d7aec21c72aefe967f107a663e1698f6e29e7a40abae1f2e13"}}